CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-03 09:22:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : fix embd when offloading non-repeating layers (#1891)

Browse Source
This commit is contained in:
Johannes Gäßler
2023-06-16 20:25:51 +02:00
committed by GitHub
parent 5b9ccaf104
commit ac3b886953
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
llama.cpp
View File

@@ -1658,7 +1658,7 @@ static bool llama_eval_internal(
// cur = cur*norm(broadcasted) // cur = cur*norm(broadcasted)
cur = ggml_mul(ctx0, cur, model.norm); cur = ggml_mul(ctx0, cur, model.norm);
offload_func_nr(cur); // offload_func_nr(cur); // TODO CPU + GPU mirrored backend
ggml_set_name(cur, "result_norm"); ggml_set_name(cur, "result_norm");
embeddings = cur; embeddings = cur;